Guardado en:
Detalles Bibliográficos
Autores principales: Jian, Wang, Jianbo, Zhou, Yuhao, Xiong, Zhenxia, Liu, Wen, Luo, LinWang, Yuan, ZhaoYuan, Yu
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.01299
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915974105530368
author Jian, Wang
Jianbo, Zhou
Yuhao, Xiong
Zhenxia, Liu
Wen, Luo
LinWang, Yuan
ZhaoYuan, Yu
author_facet Jian, Wang
Jianbo, Zhou
Yuhao, Xiong
Zhenxia, Liu
Wen, Luo
LinWang, Yuan
ZhaoYuan, Yu
contents Geometric Algebra (GA) presents challenges to learners due to its highly abstract mathematical structure and complex operational rules, as translating algebraic manipulations into concrete geometric interpretations is a non-intuitive process when developing related code. Currently, some existing GA software packages rely on manually written scripts for code generation and visualization, but their high learning curve hinders widespread adoption. Meanwhile, methods based on Large Language Models (LLMs) often produce logical errors when generating specific GA scripts, such as GAALOPScript, resulting in generally low accuracy. To address these issues, this study proposes GA-VisAgent -- a multi-agent interactive learning application for GA code generation and visualization -- building upon a Geometric algebra large language model (GAGPT). Integrating task planning mechanisms with ReAct reasoning strategies, GA-VisAgent can decompose complex operations into five standardized subtasks, including core operations like geometric products, rotations, and reflections. It supports natural language and mathematical formulas as input to automatically generate executable code, accompanied by interactive visualizations to aid user comprehension. Experimental results show that GA-VisAgent achieved a 90% code generation success rate across 40 typical Conformal GA tasks, representing a 70% improvement over GPT-4o. This application introduces an extensible new paradigm for teaching GA and developing visualization tools for related mathematical concepts. The online service for this project will be available at http://gagis.cn/gacrac.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01299
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GA-VisAgent: A Multi-Agent application for code generation and visualization in interactive learning
Jian, Wang
Jianbo, Zhou
Yuhao, Xiong
Zhenxia, Liu
Wen, Luo
LinWang, Yuan
ZhaoYuan, Yu
Machine Learning
Geometric Algebra (GA) presents challenges to learners due to its highly abstract mathematical structure and complex operational rules, as translating algebraic manipulations into concrete geometric interpretations is a non-intuitive process when developing related code. Currently, some existing GA software packages rely on manually written scripts for code generation and visualization, but their high learning curve hinders widespread adoption. Meanwhile, methods based on Large Language Models (LLMs) often produce logical errors when generating specific GA scripts, such as GAALOPScript, resulting in generally low accuracy. To address these issues, this study proposes GA-VisAgent -- a multi-agent interactive learning application for GA code generation and visualization -- building upon a Geometric algebra large language model (GAGPT). Integrating task planning mechanisms with ReAct reasoning strategies, GA-VisAgent can decompose complex operations into five standardized subtasks, including core operations like geometric products, rotations, and reflections. It supports natural language and mathematical formulas as input to automatically generate executable code, accompanied by interactive visualizations to aid user comprehension. Experimental results show that GA-VisAgent achieved a 90% code generation success rate across 40 typical Conformal GA tasks, representing a 70% improvement over GPT-4o. This application introduces an extensible new paradigm for teaching GA and developing visualization tools for related mathematical concepts. The online service for this project will be available at http://gagis.cn/gacrac.
title GA-VisAgent: A Multi-Agent application for code generation and visualization in interactive learning
topic Machine Learning
url https://arxiv.org/abs/2605.01299